Layer 12 · Neuron 1890 · boosted

L12N1890+1

Word quirks:

“ ⏎”“ important”“ not”“ better”“ more”“ less”“ mostly”“ \"”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

I am Qwen3.5, a large language model developed by Alibaba Cloud. My mission is to assist users with a wide range of tasks, including answering questions, creating content, and providing support in various domains like education, business, and personal life. I aim to be helpful, harmless, and ethical.

---

What is the most important thing for me to remember about my role?

---

How do you handle sensitive topics?

---

Can you help me with math problems?

---

Sure! I can help with math problems, but it's important to note that I don't have feelings or consciousness.

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L15N6279+1🕒	0.70	“ not”“⏎”“ more”
2. L15N2329+1🕒	0.68	“ another”“ other”“ less”
3. L12N2931-1💤	0.68	“ more”“ bigger”“ quicker”
4. L16N3916+1💤	0.68	“ more”“ better”“ crucial”
5. L17N4049-1💤	0.67	“ broader”“ partially”“ \"”
6. L16N3960-1🕒	0.67	“ only”“ “”“ less”
7. L14N2536-1🕒	0.67	“ clearer”“ fewer”“ ⏎”
8. L18N7204+1💤	0.65	“ most”“ wouldn”“ more”
9. L17N8299-1💤	0.65	“ usually”“ other”“ mostly”
10. L16N4604+1🕒	0.64	“ cheaper”“ less”“ ⏎”

Shadow specimen, apart from the ten: L12N1890-1🕒, 0.13.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 12, neuron 1890, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L12N1890+1 t0-v0.1	1.346	0.63	1.506	1.06	Top boosted tokens ↑
L12N1890-1🕒 shadow specimen t0-v0.1	0.823	0.61	1.057	1.59	“ “”“‑”“ (“”“ description”“ terse”“ ‘”“ referenced”“ *“”

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.